Upload tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +19 -0
- tokenizer.json +3 -0
- tokenizer_config.json +25 -0
.gitattributes
CHANGED
|
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<BRG>",
|
| 4 |
+
"N_00",
|
| 5 |
+
"N_01",
|
| 6 |
+
"N_02",
|
| 7 |
+
"N_03",
|
| 8 |
+
"N_04",
|
| 9 |
+
"N_05",
|
| 10 |
+
"N_06",
|
| 11 |
+
"N_07",
|
| 12 |
+
"N_08",
|
| 13 |
+
"N_09"
|
| 14 |
+
],
|
| 15 |
+
"bos_token": "<s>",
|
| 16 |
+
"eos_token": "</s>",
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"unk_token": "<unk>"
|
| 19 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa8a458a0b4246af98eeba2630a5817264d60de06571c35bcc5b9927de0d968f
|
| 3 |
+
size 14502533
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"add_special_tokens": true,
|
| 4 |
+
"additional_special_tokens": [
|
| 5 |
+
"<BRG>",
|
| 6 |
+
"N_00",
|
| 7 |
+
"N_01",
|
| 8 |
+
"N_02",
|
| 9 |
+
"N_03",
|
| 10 |
+
"N_04",
|
| 11 |
+
"N_05",
|
| 12 |
+
"N_06",
|
| 13 |
+
"N_07",
|
| 14 |
+
"N_08",
|
| 15 |
+
"N_09"
|
| 16 |
+
],
|
| 17 |
+
"bos_token": "<s>",
|
| 18 |
+
"eos_token": "</s>",
|
| 19 |
+
"name_or_path": "bigscience/bloom-560m",
|
| 20 |
+
"pad_token": "<pad>",
|
| 21 |
+
"padding_side": "left",
|
| 22 |
+
"special_tokens_map_file": null,
|
| 23 |
+
"tokenizer_class": "BloomTokenizer",
|
| 24 |
+
"unk_token": "<unk>"
|
| 25 |
+
}
|